powered by
This function is the standard method for generating weights for instances of '>Net. It uses rnorm to do so.
'>Net
rnorm
generateWeightsNormal(numUnits1, numUnits2, weights.mean = getParameter(".weights.mean", 0, ...), weights.sd = getParameter(".weights.sd", 0.01, ...), ...)
Number of units in the lower layer.
Number of units in the upper layer.
mean parameter to the rnorm function.
mean
sd parameter to the rnorm function.
sd
Additional parameters, used for parameter resolution.
Weight matrix.
Other weight generation functions: generateWeightsGlorotNormal, generateWeightsGlorotUniform, generateWeightsHeNormal, generateWeightsHeUniform, generateWeightsUniform
generateWeightsGlorotNormal
generateWeightsGlorotUniform
generateWeightsHeNormal
generateWeightsHeUniform
generateWeightsUniform
# NOT RUN { data(iris) model <- darch(Species ~ ., iris, generateWeightsFunction = "generateWeightsNormal", weights.mean = .1, weights.sd = .05) # }
Run the code above in your browser using DataLab